Add * to the list of functional tags, such as in #1356 (comment)

stanfordnlp · Jul 16, 2024 · 6b3b001 · 6b3b001
1 parent c91e3ad
commit 6b3b001
Showing 1 changed file with 5 additions and 1 deletion.
diff --git a/stanza/models/constituency/parse_tree.py b/stanza/models/constituency/parse_tree.py
@@ -18,7 +18,11 @@
 
 EMPTY_CHILDREN = ()
 
-CONSTITUENT_SPLIT = re.compile("[-=#]")
+# used to split off the functional tags from various treebanks
+# for example, the Icelandic treebank (which we don't currently
+# incorporate) uses * to distinguish 'ADJP', 'ADJP*OC' but we treat
+# those as the same
+CONSTITUENT_SPLIT = re.compile("[-=#*]")
 
 # These words occur in the VLSP dataset.
 # The documentation claims there might be *O*, although those don't